TU

Tulu3 RAG

TuluGGUF by mradermacherUpdated 2025-03-02
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Tulu3 RAG needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Tulu3 RAG – 8.03B parameter Llama model with Block‑Attention for retrieval‑augmented generation

Tulu3 RAG is an 8.03B parameter Llama model that implements Block‑Attention to reduce inference latency in RAG scenarios. The model supports a context length of 131072 tokens and is available in multiple GGUF quantizations.

Good at

  • Efficient RAG inference
  • Low TTFT and FLOPs
  • Block‑Attention flexibility

Limits

  • No vision support
  • License not specified
  • Requires 8k context for memory estimates

Best for

  • Retrieval‑augmented chat
  • Document summarization
  • Knowledge‑base querying

Who it’s for. Developers building RAG applications who need fast inference and low latency. Researchers interested in Block‑Attention performance gains.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K_S3.0 GB 4.6 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.02 GB, memory 3.6 GB) or IQ1_M (2.16 GB, 3.7 GB). For 12 GB VRAM, IQ2_S (2.76 GB, 4.3 GB) or Q2_K (3.18 GB, 4.8 GB) are suitable. Larger VRAM allows higher quality quants such as Q5_K_M (5.73 GB, 7.3 GB).

What GPU do you need for Tulu3 RAG?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Tulu3 RAG quant should you choose?

Q4_K_M is the usual starting point for Tulu3 RAG: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyTulu
Downloads (HF)971
Last updated2025-03-02

Frequently asked questions about Tulu3 RAG

How much VRAM does Tulu3 RAG need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Tulu3 RAG on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tulu3 RAG GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 18 more.

What context length does Tulu3 RAG support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Tulu3 RAG GGUF?

The files are on Hugging Face in the mradermacher/Tulu3-RAG-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Tulu3 RAG on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant, which require approximately 3.6–3.7 GB of VRAM at 8k context.

Does Tulu3 RAG support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The model was trained with a context length of 131072 tokens.

Other GGUFs of Tulu3-RAG

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Tulu models

All Tulu →

Other small models

All small models →